Gotán

Gotán

“Tango can be discussed, and we discuss it, but it encloses, as everything that is true, a secret…a French or Spanish composer who threads a tango, discovers, not without surprise, he has threaded something that our ears do not recognize, that our memory does not host, and that our body rejects it could be said that without the sunsets and evenings of Buenos Aires no tango can be made…and that this adventurous species has, however humble, its place on the universe” (Borges in Gomez, 2007/trans. A. Michalko).

Since the 1930s, musicologists and dance specialists have tried to reconstruct and “put some systematic order” into tango origins (Savigliano, 1995). The search for Argentinean tango’s beginnings and authenticity raised many discussions as some historians attribute it to African population connecting it to their rituals and music traditions; others seek its origins in the art of payadores (singers and guitar players from the inside of the country); and some in the arrival of European immigrants at the end of 19th century. The matter of which one of these groups is more entitled to tango will not be discussed here. Instead, I would like to explore and compare the style of two iconic tango orchestras: Orquesta de Francisco Canaro and Orquesta de Anibal Troilo. The orchestra of Canaro was active mostly between 1920-1940s and orchestra of Troilo after 1940s. One remarkable difference is that Canaro performed mostly with female singers whereas Troilo with male tangueros. I will analyze their dyscographies in order to find some other differences and similarities between them. Perhaps, this analyisis will reveal some secrets of tango.

Orquesta de Canaro Orquesta de Canaro

Corpus

The Corpus consists of tango songs performed by orquesta de Canaroand Orquesta de Troilo. On basis of their dyscographies and recordings, I will search for similarities and differences between those two tango orchestras. The corpus consists of 608 tracks (304 performed by Orquesta de Canaro and 304 by de Orquesta de Troilo).

Combinations

Tango means {data-width= 100, data-height=100 .storyboard}

By comparing means of danceability, tempo, valence and energy we can see some differences, however, how significant they are, still needs to be determined. The mean (M) and standard deviation (sd) of danceability feature for Canaro are 0.66 and 0.12 respectively. For Troilo M = 50 and sd = 0.10. The valence for Canaro: M = 0.71, sd = 0.14 and for Troilo: M= 0.59 and sd = 0.16. The energy for Canaro: M = 0.27, sd = 0.09 and for Troilo: M= 0.31, sd = 0.11. In general the means of Canaro’s audio features are higher than the ones of Troilo with exception of energy feature.

For both orchestras the mean of tempo is around 120: Orquesta de Canaro M = 121, sd=17.3 and Orquesta de Troilo M = 117, sd 17.1.54 and Tita sd= 24.21. Due to the significant variability of tempi across the songs the difference between the min en max values is rather large. For instance, the min and max tempo of Orquesta de Canaro is 57.56 and 193.74 respectively. For Orquesta de Troillo the min tempo is 57.24 and max tempo 186.18. Indeed, the diversity and changeability of tempi in tango is one of its fundamentals. Also, because of tango’s mutable and mercurial character, non-normal distribution in all audio features is observed. Due to these observations I will not consider extreme values of data set as outliers.

tango means

Tango means…danceability

Tango means…energy

Tango Pace

Next steps

Next steps

In the further analysis I would like to combine various variables and examine their interdependency and perhaps find some tendencies and patterns.

“If one wants eternal tango, one has to admit changing tango, because the substance of tango does not reside in the 2 for 4 nor in four for eight, but in change. And the constant change demands/requires constant searching, the constant experimentation” (Gobello,1980/Trans. A. Michalko).

Milonga

Milonga

Milonga

The tango songs recorded by Orquesta de Canaro and Orquesta de Troilo are made for dancing tango. The tango dancers are perfectly able to dance along with the music and no editing of audio is needed in order to make those audio tracks suitable for milongas. However, having in mind a non-normal distribution of variables across all data (preliminary analysis), I want to have a closer look at the relations between danceability and energy, danceability and valence and danceability and tempo.

First, I will look at the relation between danceability and energy. I grouped the observations by the name of the orchestra.

Mezclando

danceability and energy


In both cases the danceability decreases when energy increases.

danceability and Valence


There is no significant difference between interdependency of two features among Orquesta de Canaro and Orquesta de Troilo: in both cases the danceability gradually increases with the increase of the valence.

Danceability and Tempo


The scatterplot confirms the findings of preliminary analysis: the perfect tempo to dance tango seems to be ca 120.

Commentary {data-width = 100,data-height = 100, .storyboard}

The comparison of interdependencies among various audio features did not demonstrate that the recordings of two orchestras would follow individual/peculiar patterns. On contrary, in those three scatterplots, the orchestras seem to follow similar patterns. Perhaps, more detailed analysis of particular songs will reveal more differences between those tango orchestras. For instance, analysis of the same tango song.

Chromagrams

together

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Canaro

Orquesta de Canaro

Orquesta de Canaro

text

Both chromagrams illustrate tango song Silbando. The first is a version of Troilo orchestra and the second one of Canaro. The Spotify features clasify a key mode of both versions as D major. However, the A sections of the song are in d minor and B sections are in D major. Both chromagrams suggest a presence of rich harmony in two versions, especially chroma features of Canaro show a presence of almost all 12 tones throughout all the song (with exception of B and Bb). In Troilo’s version we can see better the predominance of A, G and D. It is not surprising as d/D is a Tonic, G/g a subdominant and A domimnant of d minor and D major.

Similarity matrices

both

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Canaro

Orquesta de Canaro

Orquesta de Canaro

text

The original structure of the tango song Silbando is: Intro A A’ B B’ B’(whistling) A A’ B B’ B’(whistling). The versions of Troilo and Canaro vary substantially in structure, but also in the songs’ instrumentations. Silbando of Troilo has a structure of B B’ A A’ B’’ B’’’ A’’ A’’’ B’’’’ and has lots of timbre changes. Although, the piece was originally written for a singer and piano/orchestra, this version is instrumental. It starts with soft whistling accompanied by a guitar. In the next section clearly visible on the similarity matrix (around 25s) appears section B’, which is played on accordion and guitar. Interestingly enough, Troilo does not introduce a new instrument in each new section. Instead, he makes new combinations of the same instruments (for instance, accordion + guitar, guitar + double bass, accordion + double bass); manipulates acoustic balance between them (for instance, in B and B’‘we have the same combination of instruments, however, in B the accordion is much more salient than a guitar whereas in B’’ they are even); and changes timbre through the usage of various articulations (for, instance pizzicato and bowing on strings) and dynamics. For these reasons, the similarity matrix shows many timbre novelties (substantial amount of grey/yellow lines throughout the duration of all the piece), which in its turn indicate clearly the beginning of each section.

Nevertheless, the section division marked by the timbre novelties does not necessarily coincide with the general division of similarity matrix: , for instance the timbre novelty pattern suggests that the very beginning (0-25s) of Troilo’s version has two separate segments, although, it should be treated as one (A). On the other hand, the similarity matrix interprets the middle of the piece as a single section (from 60-120s), even though, it has many more sections within it (as indicated by the timbre novelty lines). We could interpret it as a Type I Error, even though, at this moment we are able to see the structure of the piece ( as we combine information from similarity matrix general segmentation and the timbre novelty lines). However, as the consequences of this error, the further analysis might yield incorrect results, for instance, of the key chord recognition.

The version of Canaro has a structure: A A’ B B’ A’’ A’’’ B’’ B’’’ B’’’’ A’’’’ A’’’’’. It is more difficult to see this structure on the similarity matrix as it does not have so many remarkable timbre changes as a version of Troilo. In fact, the entrance of the singer in 1:03 is almost not marked/visible on the similarity matrix. The big grey/yellow line around 2:10 signalizes a timbre novelty, which in this case is whistling.

Chord Recognition

Cantro

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Troilo

Orquesta de Canaro

Orquesta de Canaro

Orquesta de Canaro

Text

In the majority of tango songs, the Spotify features failed to assign a correct key to the song. It may be due to the fact that a new section of tango song is usually played in another key mode, for instance, the A part of Silbando is in d minor and the B part in D major. The chord recognition does not work very well either. The key mode of both performances of Silbando given by Spotify API features is D Major. Nevertheless, in case of orquesta de Canaro indicates in the first section a predominance of f# minor and c# minor. Around 80s a d minor comes into play, however, from 100s the f# minor and c# minor are again predominant. Two vertical yellow lines indicate transitions between sections A and B, which as mentioned before are in different modes (A in minor key and B in major key). Interestingly enough, these are not the only places where the transition between the modes takes place. It is rather clear that chord recognition failed to indicate major modes and in case of ambiguity ca 100s “privileges” minor modes.

In case of Troilo’s version the key chord recognition is also unprecise and ambiguous. Although, from 60s till 120s the algorithm distinguishes d minor, D Major, a minor and A Major, it is unable to point out the exact changes and transitions of the chords. It might be due to the incorrect section division (see similarity matrices) but the chord recognition made per bars yields similar results. It shows the simultaneous occurrence of A major and a minor, even though, the listeners are able to distinguish clearly a chord mode of each section and bar while listening to the piece.

These examples suggest that Spotify’s tools for harmony recognition are insufficient and unable to analyze/show a complexity and richness of tango harmony. In these cases, the difficulties and ambiguities in chord recognition stem from the tuning issues, segmentation ambiguities and confusion of partials.

Cepstrograms and Timbre Coefficients comparison

cepstrograms

Timbre Coefficients

timbre coefficients Silbando

timbre coefficients Silbando

Cepstrograms

Orquesta de Canaro cepstrogram silbando Canaro

Cepstrogram Silbando Troilo

Cepstrogram Silbando Troilo

text

The comparison and analysis of timbre coefficents shows substantial differences between those two versions. The third component, which according to Spotify API correlates with spectral flatness has a very low values in Troilo’s version (from 5 till -120) and relatively high ones in Canaro’s version of this piece (from 40 till 80). It suggests that the spectral power, in case of Troilo’s performance, is concentrated in a relatively small number of bands whereas Cantro’s version has similar amount of power in all spectral bands. Furthermore, the difference in components 5, 6 and 7 is observed. Although, Spotify API does not specify with which acoustic features those components correlate, a possible candidates are: Log Spectral Spread and Roll- off, Spectral Irregularity or Spectral Entropy. However, which ones precisely still needs to be determined.

The individual cepstrograms of these two versions confirm the previous comparison.

Classifier

K-Nearest Neighbors Classification

Heatmap k-nearest neighbors

Heatmap k-nearest neighbors


The k-nearest neighbors algorithm classified Canaro’s 70 songs (out of 304) as Troilo’s and Troilo’s 54 songs (out of 304) as Canaro’s. It has 0.796 accuracy, kap 0.592 and j_ind 0.592.

Random Forest

Random Forest

Random Forest


The results of Random Forest suggest three audio features that are the most helpful in distinguishing between Cantro’s and Troilo’s recordings: danceability feature, Timbre Component 11 and Timbre Component 06.

Reduced knn

Reduced knn

Reduced knn


In the reduced version of knn only top three features were used: Timbre Component 06, Danceability and Timbre Component 11. Surprisingly enough, it has lower accuracy than the previous model: 0.690, kap 0.381 and j_ind 0.381. As a consequence it classified 95 songs of Canaro as of Troiolo’s and 93 songs of Troilo as of Canaro’s.

Clustering

both

Hierarchical clustering

Hierarchical clustering random sample

Hierarchical clustering random sample

Heatmap

[1] 432.0 345.6

both

For the better readability of the hierarchical cluster the random sample of 50 songs has been derived from the main sample 608 songs. As we can see it is divided into two main brunches, which further divide sample into three subbrunches. Ideally (taking into account the research question), the first main brunch could correspond to the oruqesta de Canaro and the other to Orquesta de Troilo, however, it is not a case. The songs of both groups are mingled with eachother across the cluster tree. Having a glimpse at the heatmap we can presume that the influance on the clustering had instrumentalness, speechiness, chroma G and some timbre coefficients. Nevertheless, there is no precise clear-cut relationship between one audio feature or a group of features and this hierarchical clustering.

Moreover,the relistening of the pieces did not help to understand which features separate these clusters. It may be due to the fact that the features responsibile for brunching are not easly perceivable by only listening to the audios or that the cluster analysis is not really stable.

Ultima curva

  1. Project made by Aleksandra Michalko as a part of the course Computational Musicology at the University of Amsterdam given by/lectured by Dr John Ashley Burgoyne.

References: Gobello, J. (1980). CrĂłnica general del tango (No. 78 (091)). Fraterna. Gomez, A. (2009). Ultimo patio. Turmalina. Savigliano, M. (1995). Tango and the political economy of passion. Westview Press.